Noisy ecological data enhancement via spatiotemporal interpolation and variance mapping

Abstract

In some embodiments, a computer-implemented method of training and using a machine learning model is provided. A computing system receives a plurality of sampling data values for a geographical area. The computing system creates an interpolated value map and a variance map for the geographical area using the plurality of sampling data values. The computing system trains a machine learning model using values of the interpolated value map as ground truth values and evaluating performance of the machine learning model using the variance map. The computing system stores the trained machine learning model in a model data store.

What is claimed is: 
     
         1 . A computer-implemented method of training and using a machine learning model, the method comprising:
 receiving, by a computing system, a plurality of sampling data values for a geographical area;   creating, by the computing system, an interpolated value map and a variance map for the geographical area using the plurality of sampling data values;   training, by the computing system, a machine learning model using values of the interpolated value map as ground truth values and evaluating performance of the machine learning model using the variance map; and   storing, by the computing system, the trained machine learning model in a model data store.   
     
     
         2 . The computer-implemented method of  claim 1 , further comprising:
 generating, by the computing system, a predicted value for the geographical area using the trained machine learning model.   
     
     
         3 . The computer-implemented method of  claim 2 , further comprising:
 receiving, by the computing system, one or more input values from a user interface;   wherein generating the predicted value for the geographical area using the trained machine learning model includes providing the one or more input values received from the user interface as input to the trained machine learning model.   
     
     
         4 . The computer-implemented method of  claim 1 , wherein creating the interpolated value map and the variance map includes performing kriging over at least a portion of the plurality of sampling data values to generate both the interpolated value map and the variance map. 
     
     
         5 . The computer-implemented method of  claim 1 , wherein evaluating performance of the machine learning model using the variance map includes:
 determining a difference between a value predicted by the machine learning model and a corresponding ground truth value of the interpolated value map; and   weighting the difference by a variance value of the variance map corresponding to the ground truth value of the interpolated value map.   
     
     
         6 . The computer-implemented method of  claim 5 , wherein determining the difference between the value predicted by the machine learning model and the corresponding ground truth value of the interpolated value map, and weighting the difference by the variance value of the variance map corresponding to the ground truth value of the interpolated value map includes performing a log-likelihood comparison. 
     
     
         7 . The computer-implemented method of  claim 1 , wherein each sampling data value of the plurality of sampling data values includes a latitude, a longitude, and a timestamp. 
     
     
         8 . The computer-implemented method of  claim 1 , wherein each sampling data value of the plurality of sampling data values includes a count value. 
     
     
         9 . The computer-implemented method of  claim 8 , wherein the count value is a count of animals detected by a trap. 
     
     
         10 . The computer-implemented method of  claim 1 , wherein training the machine learning model includes updating the machine learning model using gradient descent. 
     
     
         11 . A non-transitory computer-readable medium having computer-executable instructions stored thereon that, in response to execution by one or more processors of a computing system, cause the computing system to perform actions for training and using a machine learning model, the actions comprising:
 receiving, by the computing system, a plurality of sampling data values for a geographical area;   creating, by the computing system, an interpolated value map and a variance map for the geographical area using the plurality of sampling data values;   training, by the computing system, a machine learning model using values of the interpolated value map as ground truth values and evaluating performance of the machine learning model using the variance map; and   storing, by the computing system, the trained machine learning model in a model data store.   
     
     
         12 . The non-transitory computer-readable medium of  claim 11 , wherein the actions further comprise:
 generating, by the computing system, a predicted value for the geographical area using the trained machine learning model.   
     
     
         13 . The non-transitory computer-readable medium of  claim 12 , wherein the actions further comprise:
 receiving, by the computing system, one or more input values from a user interface;   wherein generating the predicted value for the geographical area using the trained machine learning model includes providing the one or more input values received from the user interface as input to the trained machine learning model.   
     
     
         14 . The non-transitory computer-readable medium of  claim 11 , wherein creating the interpolated value map and the variance map includes performing kriging over at least a portion of the plurality of sampling data values to generate both the interpolated value map and the variance map. 
     
     
         15 . The non-transitory computer-readable medium of  claim 11 , wherein evaluating performance of the machine learning model using the variance map includes:
 determining a difference between a value predicted by the machine learning model and a corresponding ground truth value of the interpolated value map; and   weighting the difference by a variance value of the variance map corresponding to the ground truth value of the interpolated value map.   
     
     
         16 . The non-transitory computer-readable medium of  claim 15 , wherein determining the difference between the value predicted by the machine learning model and the corresponding ground truth value of the interpolated value map, and weighting the difference by the variance value of the variance map corresponding to the ground truth value of the interpolated value map includes performing a log-likelihood comparison. 
     
     
         17 . The non-transitory computer-readable medium of  claim 11 , wherein each sampling data value of the plurality of sampling data values includes a latitude, a longitude, and a timestamp. 
     
     
         18 . The non-transitory computer-readable medium of  claim 11 , wherein each sampling data value of the plurality of sampling data values includes a count value. 
     
     
         19 . The non-transitory computer-readable medium of  claim 18 , wherein the count value is a count of animals detected by a trap. 
     
     
         20 . The non-transitory computer-readable medium of  claim 11 , wherein training the machine learning model includes updating the machine learning model using gradient descent.